The first version of Veyra, these models are meant for local CPU inference.
Veyra AI
community
AI & ML interests
Building tiny English language models for practical local AI. Veyra AI focuses on CPU-friendly inference, function calling, tool use, Python-oriented small models, distillation, RLVR, and lightweight fine-tuning. The goal is to make compact models that are easy to run, inspect, adapt, and use in real workflows without large hardware.
Recent Activity
View all activity
The second generation of Veyra.
-
veyra-ai/Veyra2-Apricot-50M-Base
Text Generation • 49.3M • Updated • 1.04k • 12 -
veyra-ai/Veyra2-Mango-30M-Base
Text Generation • 30.7M • Updated • 292 • 6 -
veyra-ai/Veyra2-Mango-15M-Base
Text Generation • 15.7M • Updated • 348 • 4 -
veyra-ai/Veyra2-Mango-30M-Base-ONNX
Text Generation • Updated • 64 • 1
The first version of Veyra, these models are meant for local CPU inference.
The second generation of Veyra.
-
veyra-ai/Veyra2-Apricot-50M-Base
Text Generation • 49.3M • Updated • 1.04k • 12 -
veyra-ai/Veyra2-Mango-30M-Base
Text Generation • 30.7M • Updated • 292 • 6 -
veyra-ai/Veyra2-Mango-15M-Base
Text Generation • 15.7M • Updated • 348 • 4 -
veyra-ai/Veyra2-Mango-30M-Base-ONNX
Text Generation • Updated • 64 • 1